{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DMQ7ZH3IPZPBUTWHLCJ3EPP7G4","short_pith_number":"pith:DMQ7ZH3I","canonical_record":{"source":{"id":"2510.10544","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-12T11:02:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f2e7a29ce1fa03aac2cdee0a7931d6897d2fdb712e4f9e35c31a42ae90e9a119","abstract_canon_sha256":"6237a912791af49ee13694327c9b77cd36a2ef3f4cece95a5ed01edcd3561964"},"schema_version":"1.0"},"canonical_sha256":"1b21fc9f687e5e1a4ec75893b23dff3738de2d696c601af3f732dbbe54c60fcf","source":{"kind":"arxiv","id":"2510.10544","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10544","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10544v3","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10544","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"DMQ7ZH3IPZPB","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"DMQ7ZH3IPZPBUTWH","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"DMQ7ZH3I","created_at":"2026-06-01T01:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DMQ7ZH3IPZPBUTWHLCJ3EPP7G4","target":"record","payload":{"canonical_record":{"source":{"id":"2510.10544","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-12T11:02:18Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f2e7a29ce1fa03aac2cdee0a7931d6897d2fdb712e4f9e35c31a42ae90e9a119","abstract_canon_sha256":"6237a912791af49ee13694327c9b77cd36a2ef3f4cece95a5ed01edcd3561964"},"schema_version":"1.0"},"canonical_sha256":"1b21fc9f687e5e1a4ec75893b23dff3738de2d696c601af3f732dbbe54c60fcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:23.440031Z","signature_b64":"vIECj7VXkB7XNPK5g5zKKWD4R6nM8xUIbdVMCu8tVzGUQBeQsgSC//g6THimmnCmaHiBCQ8U3z8xWsyEC7EjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b21fc9f687e5e1a4ec75893b23dff3738de2d696c601af3f732dbbe54c60fcf","last_reissued_at":"2026-06-01T01:02:23.439300Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:23.439300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.10544","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nKVnAtoAWk3WrUxcuqELQCzT5Ysh8/tNc/9Z9HwNtCU6U19SeR0Ju5wsW3CJrcoTpz7EVmik0wunvNJemykgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:02:20.569794Z"},"content_sha256":"79188d3371e3b4276b07d0e207e0fc8ea16dd57b344543119db42dc8369fd78d","schema_version":"1.0","event_id":"sha256:79188d3371e3b4276b07d0e207e0fc8ea16dd57b344543119db42dc8369fd78d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DMQ7ZH3IPZPBUTWHLCJ3EPP7G4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAC-Bayesian Reinforcement Learning Trains Generalizable Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdelkrim Zitouni, Juba Agoun, Mehdi Hennequin, Nadia Kabachi, Omar Rivasplata, Ryan Horache","submitted_at":"2025-10-12T11:02:18Z","abstract_excerpt":"We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in obtaining generalization guarantees for reinforcement learning, where the sequential nature of data breaks the independence assumptions underlying classical bounds. The new bound provides non-vacuous certificates for modern off-policy algorithms such as Soft Actor-Critic. We demonstrate the practical utility of the bound through PB-SAC, a novel algorithm that optimizes the bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10544","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.10544/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O21jGPvziLSuppmyBDmjRU3L2Cb0oVa5UvAfPMuxlrgCYyk7EdCE6MDruUQy7ZmkTbgXwMwVuUenmMHwRwG+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:02:20.570180Z"},"content_sha256":"36475db6075fec5ac44f6749a7925b17287ffc2676d5364fc60e5bdec6ccf236","schema_version":"1.0","event_id":"sha256:36475db6075fec5ac44f6749a7925b17287ffc2676d5364fc60e5bdec6ccf236"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4/bundle.json","state_url":"https://pith.science/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T07:02:20Z","links":{"resolver":"https://pith.science/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4","bundle":"https://pith.science/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4/bundle.json","state":"https://pith.science/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMQ7ZH3IPZPBUTWHLCJ3EPP7G4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DMQ7ZH3IPZPBUTWHLCJ3EPP7G4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6237a912791af49ee13694327c9b77cd36a2ef3f4cece95a5ed01edcd3561964","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-12T11:02:18Z","title_canon_sha256":"f2e7a29ce1fa03aac2cdee0a7931d6897d2fdb712e4f9e35c31a42ae90e9a119"},"schema_version":"1.0","source":{"id":"2510.10544","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10544","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10544v3","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10544","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"DMQ7ZH3IPZPB","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"DMQ7ZH3IPZPBUTWH","created_at":"2026-06-01T01:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"DMQ7ZH3I","created_at":"2026-06-01T01:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:36475db6075fec5ac44f6749a7925b17287ffc2676d5364fc60e5bdec6ccf236","target":"graph","created_at":"2026-06-01T01:02:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.10544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in obtaining generalization guarantees for reinforcement learning, where the sequential nature of data breaks the independence assumptions underlying classical bounds. The new bound provides non-vacuous certificates for modern off-policy algorithms such as Soft Actor-Critic. We demonstrate the practical utility of the bound through PB-SAC, a novel algorithm that optimizes the bound","authors_text":"Abdelkrim Zitouni, Juba Agoun, Mehdi Hennequin, Nadia Kabachi, Omar Rivasplata, Ryan Horache","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-12T11:02:18Z","title":"PAC-Bayesian Reinforcement Learning Trains Generalizable Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10544","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79188d3371e3b4276b07d0e207e0fc8ea16dd57b344543119db42dc8369fd78d","target":"record","created_at":"2026-06-01T01:02:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6237a912791af49ee13694327c9b77cd36a2ef3f4cece95a5ed01edcd3561964","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-12T11:02:18Z","title_canon_sha256":"f2e7a29ce1fa03aac2cdee0a7931d6897d2fdb712e4f9e35c31a42ae90e9a119"},"schema_version":"1.0","source":{"id":"2510.10544","kind":"arxiv","version":3}},"canonical_sha256":"1b21fc9f687e5e1a4ec75893b23dff3738de2d696c601af3f732dbbe54c60fcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b21fc9f687e5e1a4ec75893b23dff3738de2d696c601af3f732dbbe54c60fcf","first_computed_at":"2026-06-01T01:02:23.439300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:23.439300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vIECj7VXkB7XNPK5g5zKKWD4R6nM8xUIbdVMCu8tVzGUQBeQsgSC//g6THimmnCmaHiBCQ8U3z8xWsyEC7EjBw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:23.440031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.10544","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79188d3371e3b4276b07d0e207e0fc8ea16dd57b344543119db42dc8369fd78d","sha256:36475db6075fec5ac44f6749a7925b17287ffc2676d5364fc60e5bdec6ccf236"],"state_sha256":"543a407ba88f7c1d9b1e031906cc92c613d13e18176c42689e6defeda35d3ef4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rw7N/zCAIFRaadq94o4fXqN52C6nqeKkXmYDy/9E6FiXciG8+iMrLmgxjLjf9VkRwGeEHZm4CvHBT0wwcqTWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T07:02:20.572441Z","bundle_sha256":"4f838fd12148e825b4b5397d2a95512d78d656155050d8d44da1c084947a1438"}}